公开(公告)号：US11754750B1

公开(公告)日：2023-09-12

申请号：US18171320

申请日：2023-02-17

Applicant: Jack T Ma

Inventor： Jack T Ma

IPC: G06F16/29 ,  G01W1/10

CPC classification number: G01W1/10 ,  G06F16/29 ,  G01W2201/00

Abstract: A method and system is presented for short to long-term flood forecasting. At the core of the method is a neural network-based flood forecasting model. The method and system performs the steps to implement and use the neural network-based flood forecasting model comprising obtaining historical data from the region, including but not limited to climate and water level data; sampling and structuring the historical data in conjunction with data queried from a GIS (geographic information system) into a dataset; dividing the dataset into pre-processed training and validation partitions; configuring the neural network and training hyperparameters; training the neural network-based flood forecasting model on the pre-processed training partition; performing validation on the neural network-based flood forecasting model with the pre-processed validation partition. Embodiments of the invention are capable of performing flood forecasting over a region in short to long-term time intervals.

公开(公告)号：US11719858B2

公开(公告)日：2023-08-08

申请号：US17055432

申请日：2019-05-14

Applicant: BASF Agro Trademarks GmbH

Inventor： Mirwaes Wahabzada ,  Holger Hoffmann ,  Eva Hill ,  Ole Peters ,  Christian Kerkhoff ,  Umit Baran Ilbasi ,  Priyamvada Shankar

IPC: G01W1/10 ,  G06F30/27 ,  G01W1/06 ,  G06N20/00 ,  H04W4/021

CPC classification number: G01W1/10 ,  G01W1/06 ,  G06F30/27 ,  G01W2201/00 ,  G01W2203/00 ,  G06N20/00 ,  H04W4/021 ,  Y02A90/10

Abstract: A method performed by at least one apparatus is inter alia disclosed, said method comprising: obtaining weather model data indicative of location-specific weather information for a first set of locations (26) on a first grid (28); obtaining an area of interest (30) associated to at least one user (32); obtaining and/or determining a second set of locations (34) based on a second grid (36) within said area of interest (30); obtaining measurement data on location-specific weather information of a measurement device associated to said at least one user located at a measurement location (38) within and/or proximate to said area of interest (30); and determining, based on at least said obtained weather model data and said obtained measurement data, location-specific weather information for said second set of locations (34) based on said second grid (36).

公开(公告)号：US20170336534A1

公开(公告)日：2017-11-23

申请号：US15600020

申请日：2017-05-19

Applicant: THE CATHOLIC UNIVERSITY OF AMERICA

Inventor： Kevin F. Forbes ,  Ernest M. Zampelli

IPC: G01W1/10 ,  G06F17/30 ,  G06F15/18 ,  G06F17/10 ,  G01W1/00

CPC classification number: G01W1/10 ,  F05B2260/8211 ,  G01W2001/006 ,  G01W2201/00 ,  G01W2203/00 ,  G06F16/23 ,  G06F17/10 ,  G06F17/18 ,  G06N20/00 ,  G06Q10/04 ,  G06Q50/06

Abstract: A computer system and method for improving the accuracy of predictions of the amount of renewable energy, such as solar energy and wind energy, available to an electric utility, and/or refine such predictions, by providing improved integration of meteorological forecasts. Coefficient values are calculated for a renewable energy generation model by performing a regression analysis with the forecasted level of renewable energy posted by the utility, forecasted weather conditions and measures of seasonality as explanatory variables. Accuracy is further enhanced through the inclusion of a large number of time series variables that reflect the systematic nature of the energy/weather system. The model also uses the original forecast posted by the system operator as well as variables to control for season.